dynamodb-table-design
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files containing access patterns, which serves as a potential ingestion point for indirect prompt injection attacks.\n
- Ingestion points: The design workflow in
SKILL.mdrequires the agent to read an external access patterns markdown file to begin the design process.\n - Boundary markers: The instructions do not define specific boundary markers or delimiters to isolate the content of the access patterns file from the agent's system instructions.\n
- Capability inventory: The skill utilizes the agent's capability to read and write files, specifically persisting the final table design to the filesystem as described in
SKILL.md.\n - Sanitization: Validation is performed on the logical structure of the data (e.g., checking for IDs and parameters), but no sanitization is performed to detect or neutralize potential prompt injection attacks within the document text.
Audit Metadata